Title :
Texture and neural network for road segmentation
Author :
Fernandez-Maloigne, Christine ; Bonnet, William
Author_Institution :
Univ. of Technol., Compiegne, France
Abstract :
Road recognition is a main component in autonomous vehicle guidance system. We aim to determine whether an image element is part of the road or not, by using information from the element´s proximity. The wide range of situations have to be processed is a problem, and they impose on the system a capacity of self-adaptation to new cases. A neural network based architecture has been chosen to implement the texture analysis. By applying a local texture recognition process to the whole image, we obtain a segmented image of the road
Keywords :
computer vision; image segmentation; image texture; navigation; neural nets; object recognition; road vehicles; autonomous vehicle guidance system; computer vision; local texture recognition; neural network; road recognition; road segmentation; texture analysis; Artificial neural networks; Image segmentation; Mobile robots; Navigation; Neural networks; Pixel; Postal services; Remotely operated vehicles; Road vehicles; Working environment noise;
Conference_Titel :
Intelligent Vehicles '95 Symposium., Proceedings of the
Conference_Location :
Detroit, MI
Print_ISBN :
0-7803-2983-X
DOI :
10.1109/IVS.1995.528305
